Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach

Breast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering...

Full description

Saved in:
Bibliographic Details
Published in:Cancers Vol. 15; no. 10; p. 2704
Main Authors: Bobowicz, Maciej, Rygusik, Marlena, Buler, Jakub, Buler, Rafał, Ferlin, Maria, Kwasigroch, Arkadiusz, Szurowska, Edyta, Grochowski, Michał
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 10.05.2023
MDPI
Subjects:
Algorithms
Artificial intelligence
Breast cancer
Cancer
Classification
Comparative analysis
Data mining
Datasets
Deep learning
Diagnosis
Lesions
Machine learning
Mammography
Medical diagnosis
Oncology, Experimental
Transfer learning
scarcity of data
attention maps
breast cancer
multimodal learning
machine learning
weakly supervised learning
digital mammography
artificial intelligence
breast lesion classification
ISSN:2072-6694, 2072-6694
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Breast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private dataset with 1174 non-cancer and 794 cancer images labelled at the image level with pathological ground truth confirmation. We used feature extractors (ResNet-18, ResNet-34, ResNet-50 and EfficientNet-B0) pre-trained on ImageNet. The best results were achieved with multimodal-view classification using both CC and MLO images simultaneously, resized by half, with a patch size of 224 px and an overlap of 0.25. It resulted in AUC-ROC = 0.896 ± 0.017, F1-score 81.8 ± 3.2, accuracy 81.6 ± 3.2, precision 82.4 ± 3.3, and recall 81.6 ± 3.2. Evaluation with the Chinese Mammography Database, with 5-fold cross-validation, patient-wise breakdowns, and transfer learning, resulted in AUC-ROC 0.848 ± 0.015, F1-score 78.6 ± 2.0, accuracy 78.4 ± 1.9, precision 78.8 ± 2.0, and recall 78.4 ± 1.9. The CLAM algorithm’s attentional maps indicate the features most relevant to the algorithm in the images. Our approach was more effective than in many other studies, allowing for some explainability and identifying erroneous predictions based on the wrong premises.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-6694
2072-6694
DOI:10.3390/cancers15102704